Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered structurally. The description adds genuinely new behavior beyond that: it never raises protocol errors and instead returns {"error": "<what is wrong and how to fix it>"} with a concrete example, which materially changes how an agent should handle failure and retry. Its final sentence restating read-only/idempotent is redundant with the annotations, so it falls just short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first line, followed by interval rules, an example, usage guidance, and error semantics in a logical order with no filler sentences. The inline JSON example is slightly long and partially duplicates the available output schema, which is the only reason it is not a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read-only computation with an output schema already present, the description covers everything an agent needs: what it computes, the interval formula, input/output shape, sibling disambiguation, and non-throwing error contract with retry safety. Nothing required to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both start_date and sessions are already documented, and the baseline would be 3. The description adds value beyond the schema by working through a concrete call ('{start_date: 2026-09-01, sessions: 4}' returns start plus a reviews array with session, day_offset, date), which clarifies how inputs map to the expanding-interval output rather than just restating field names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Build a spaced-repetition review schedule') and immediately pins down the defining behavior: expanding intervals of 1, 3, 7, 14, 30, 60, 120, 240 days. It explicitly names the sibling it is not (lesson_timer for a single session), so an agent can disambiguate without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive trigger ('Use when material must be reviewed on expanding intervals') and an explicit exclusion with the named alternative ('Not for timing a single session, which the educator server's lesson_timer handles'). Both the when and the when-not are stated, leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.